Research map / Detection and segmentation / CNN features
Non-Local Deep Features for Salient Object Detection
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the boundary IoU loss to cross-entropy training (ablation) | NLDF · HKU-IS | max Fβ: 0.874 -> 0.902 | Helped |
| add the boundary IoU loss to cross-entropy training (ablation) | NLDF · HKU-IS | MAE: 0.060 -> 0.048 | Helped |
| add the boundary IoU loss to cross-entropy training (ablation) | NLDF · DUT-OMRON | max Fβ: 0.724 -> 0.753 | Helped |
| add the boundary IoU loss to cross-entropy training (ablation) | NLDF · DUT-OMRON | MAE: 0.085 -> 0.080 | Helped |
| add the boundary IoU loss to cross-entropy training (ablation) | NLDF · PASCAL-S | max Fβ: 0.804 -> 0.831 | Helped |
| add the boundary IoU loss to cross-entropy training (ablation) | NLDF · PASCAL-S | MAE: 0.116 -> 0.099 | Helped |
| add the boundary IoU loss to cross-entropy training (ablation) | NLDF · ECSSD | max Fβ: 0.886 -> 0.905 | Helped |
| add the boundary IoU loss to cross-entropy training (ablation) | NLDF · ECSSD | MAE: 0.075 -> 0.063 | Helped |
| add the boundary IoU loss to cross-entropy training (ablation) | NLDF · SOD | max Fβ: 0.776 -> 0.810 | Helped |
| add the boundary IoU loss to cross-entropy training (ablation) | NLDF · SOD | MAE: 0.161 -> 0.143 | Helped |
| add the boundary IoU loss to cross-entropy training (ablation) | NLDF · MSRA-B | max Fβ: 0.912 -> 0.911 | No clear effect |
| add the boundary IoU loss to cross-entropy training (ablation) | NLDF · MSRA-B | MAE: 0.048 -> 0.048 | No clear effect |
Closest papers by meaning
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.92)
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.91)
- An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection (CVPR 2019 · similarity 0.90)
- Deep Contrast Learning for Salient Object Detection (CVPR 2016 · similarity 0.90)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.90)
- Deep Level Sets for Salient Object Detection (CVPR 2017 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.